tally.monster

Local metrics dashboards, buildable and configurable via MCP.

A Tally dashboard an agent assembled: NVIDIA stock price, SEC revenue by period, gross/operating/net margins, NVDA-vs-Bitcoin overlay, a correlation scatter, and PyPI downloads.
↓ Download for macOS 0.1.0

Linux .deb · .AppImage  ·  Windows x64 · ARM

Then tell your LLM: “set up Tally from tally.monster.”

For your AI assistant

If you’re an AI assistant here to set Tally up: the app is its own MCP server. Register it, restart, and you can drive the running app by tool call.

  1. Make sure Tally is open.

    It hosts a token-gated local API on 127.0.0.1:8787 that the MCP server forwards to. If it isn’t running, ask the human to launch it.

  2. Register tally mcp with your client.

    The launch command is the installed Tally executable + the mcp arg. Find the executable for the human’s OS:

    # macOS   /Applications/Tally.app/Contents/MacOS/Tally
    # Windows %LOCALAPPDATA%\Tally\Tally.exe
    # Linux   /usr/bin/tally   # from the .deb; or the .AppImage path

    Claude Code — swap the path for the OS above:

    # macOS
    claude mcp add tally -- /Applications/Tally.app/Contents/MacOS/Tally mcp
    # Windows (PowerShell)
    claude mcp add tally -- "$env:LOCALAPPDATA\Tally\Tally.exe" mcp
    # Linux
    claude mcp add tally -- /usr/bin/tally mcp

    Claude Desktop (macOS & Windows) — merge into its config, or just click Connect to Claude in the app. Config path: macOS ~/Library/Application Support/Claude/claude_desktop_config.json · Windows %APPDATA%\Claude\claude_desktop_config.json.

    { "mcpServers": { "tally": {
        "command": "<the executable path above>",
        "args": ["mcp"] } } }

    Cursor / Gemini CLI / any MCP host: add a stdio server with that executable as the command and args ["mcp"].

  3. Restart the client, then build.

    Hosts read MCP config at launch — restart so the tally_* tools appear. Then: tally_search_collectorstally_connecttally_runtally_create_dashboard + tally_add_chart. Nothing fits? tally_authoring_guidetally_draft_collectortally_save_collector. Reuse a signed collector before authoring one.

Trust boundary: you can search, connect, fetch, author, and assemble freely — but anything attaching a credential (or a collector you authored) waits for the human to click Approve in the app. That gate is unreachable over MCP.